A Recurrent Neural Network for N-Stage Optimal Control Problems

Authors:
Li-Zhi Liao
Affiliations:
Department of Mathematics, Hong Kong Baptist University, Kowloon Tong, Kowloon, Hong Kong, e-mail: liliao@hkbu.edu.hk
Venue:
Neural Processing Letters
Year:
1999

Citing 1
Cited 1

Learning a trajectory using adjoint functions and teacher forcing

Neural Networks

On the Computational Complexity of Binary and Analog Symmetric Hopfield Nets

Neural Computation

Quantified Score

Hi-index	0.00

Visualization

Abstract

A recurrent neural network is introduced for the N-stage optimalcontrol problem. The new neural network is based on a reformulationof the original optimal control problem and the gradient method.The simulation results on two examples indicate that the new neuralnetwork is quite effective.